JP2022131018A - Information providing device and information providing system - Google Patents

Abstract

To provide an information providing device and an information providing system capable of accurately calculating a degree of risk of a behavior of a vehicle.SOLUTION: An information providing device 20 includes: a collection unit 231; and a calculation unit 233. The collection unit collects detection information containing a sensor value detected by an on-vehicle device mounted on a vehicle, and vehicle information related to the vehicle. The calculation unit calculates a degree of risk of a behavior of the vehicle on the basis of the detection information and the vehicle information. For instance, the information providing device calculates the degree of risk by multiplying a G value by a weight corresponding to vehicle size.SELECTED DRAWING: Figure 2

Description

The present invention relates to an information providing device and an information providing system.

2. Description of the Related Art Conventionally, there is known a technique of associating a video imaged by an in-vehicle device with a danger pattern. Also, there is known a technique for scoring the degree of risk of vehicle behavior (eg, number of near-miss occurrences/travel distance) based on information such as the G value obtained by a business-use drive recorder.

JP 2020-52634 A

However, with conventional techniques, there are cases where the degree of danger of vehicle behavior cannot be calculated accurately.

For example, in the conventional technology, the detected G value may be regarded as the degree of risk, but other information is not taken into account, so it may not be realistic. Moreover, in the conventional technology, even if the event that occurred is the same, the calculation result may differ depending on the model of the in-vehicle device.

SUMMARY OF THE INVENTION It is an object of the present invention to accurately calculate the degree of risk of vehicle behavior.

In order to solve the above-described problems and achieve the object, an information providing device according to the present invention has a collection unit and a calculation unit. The collection unit collects detection information including sensor values detected by an in-vehicle device mounted in the vehicle, and vehicle information about the vehicle. The calculation unit calculates the degree of risk of behavior of the vehicle based on the detection information and the vehicle information.

According to the present invention, it is possible to accurately calculate the degree of risk of vehicle behavior.

FIG. 1 is a diagram illustrating an information providing system according to an embodiment. FIG. 2 is a diagram illustrating a configuration example of an information providing device according to the embodiment; FIG. 3 is a diagram showing an example of danger information. FIG. 4 is a diagram showing an example of score calculation. FIG. 5 is a diagram showing an example of score calculation. FIG. 6 is a flow chart showing a processing procedure of the information providing device according to the embodiment.

Hereinafter, embodiments of an information providing device and an information providing system disclosed in the present application will be described in detail with reference to the accompanying drawings. In addition, this invention is not limited by embodiment shown below.

First, the configuration and processing of the information providing system according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an information providing system according to an embodiment.

As shown in FIG. 1, the information providing system 1 has a vehicle V, an in-vehicle device 10, an information providing device 20, and a terminal 30. FIG. For example, vehicle V is an automobile.

For example, the in-vehicle device 10 is a drive recorder installed inside the vehicle V. FIG. Further, for example, the information providing device 20 is a server. Also, for example, the terminal 30 is a personal computer, a smart phone, or the like.

Also, the in-vehicle device 10 and the terminal 30 are connected to the information providing device 20 via the network N so as to be capable of data communication. For example, network N is the Internet.

The flow of processing of the information providing system 1 will be described with reference to FIG. As shown in FIG. 1, first, the in-vehicle device 10 performs detection (step S1).

For example, the in-vehicle device 10 measures the G value using a G sensor and detects when the G value becomes equal to or greater than a predetermined value. Also, the in-vehicle device 10 photographs the inside or surroundings of the vehicle V with a camera.

Next, the in-vehicle device 10 transmits the detection information and the vehicle information to the information providing device 20 (step S2).

The detection information includes sensor values such as G values. Further, the vehicle information is, for example, physical characteristics of the vehicle V, and may be represented by a vehicle class.

For example, the vehicle class is determined based on the length, width, weight, number of passengers, load capacity, engine displacement, shape, running performance, and the like of the vehicle V.

In-vehicle device 10 may transmit a picture with detection information, when a picture is picturized.

The information providing device 20 calculates a score based on the detection information and vehicle information (step S3). The score is an example of the degree of danger of behavior of the vehicle V. FIG.

The information providing device 20 notifies the terminal 30 of the calculated score (step S4). The information providing device 20 may notify the in-vehicle device 10 of the score.

In this way, the information providing device 20 can calculate a score that takes into consideration not only the detection results such as the G value, but also the physical characteristics such as the vehicle class.

The configuration of the information providing device 20 will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of an information providing device according to the embodiment;

As shown in FIG. 2 , the information providing device 20 has an interface section 21 , a storage section 22 and a control section 23 .

The interface unit 21 is an interface for inputting and outputting data. For example, the interface unit 21 is a NIC (Network Interface Card). The interface unit 21 can transmit and receive data to and from other devices.

Also, the interface unit 21 may be connected to an input device such as a mouse or a keyboard. Also, the interface unit 21 may be connected to an output device such as a display and a speaker.

The control unit 23 and the storage unit 22 of the information providing device 20 are, for example, a computer having a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), a flash memory, an input/output port, and various circuits. It is realized by

The storage unit 22 stores danger information 221 . The danger information 221 is information relating to cases such as past near misses and accidents. FIG. 3 is a diagram showing an example of danger information.

As shown in FIG. 3, the danger information 221 includes items such as vehicle class, loading condition, danger type, G value, and accident. The items shown in FIG. 3 are examples, and the danger information 221 may include other items.

The vehicle class of the danger information 221 is information representing the physical characteristics of the vehicle. Here, the vehicle class is determined mainly by the size and engine displacement of the vehicle, such as "large vehicle", "compact car", "midsize car", and "light vehicle". Note that the vehicle class may be represented by a continuous value proportional to the weight of the vehicle or the like.

The loading state of the danger information 221 is information related to the persons on board the vehicle and the cargo loaded.

The danger type of the danger information 221 is the type of dangerous event recognized from the image or the like of the in-vehicle device installed in the vehicle. Also, the danger type may be estimated based on sensor values other than images, such as G sensors and GPS trackers.

Note that the danger type may be left blank because it may not be possible to obtain it especially if there is no image.

The G value of the danger information 221 is a G value detected by an in-vehicle device mounted on the vehicle.

The accident of danger information 221 is information for distinguishing whether or not an accident has actually occurred.

For example, in the second row of FIG. 3, a G value of 1.0 is detected when a vehicle with a vehicle class of “large size vehicle” is in a state where one passenger is loaded with luggage (loaded). , indicates that no accident occurred (non-occurrence).

Also, for example, in the tenth line of FIG. is detected, indicating that an accident has occurred.

The control unit 23 has a collection unit 231 , an extraction unit 232 , a calculation unit 233 and a notification unit 234 .

The collection unit 231 collects detection information including sensor values detected by an in-vehicle device mounted in the vehicle, and vehicle information about the vehicle. In addition, the collection unit 231 further collects images captured by the in-vehicle device.

Although only the in-vehicle device 10 is shown in FIG.

Sensing information includes sensor values such as G-sensors and GPS trackers.

Vehicle information includes physical characteristics of the vehicle. The vehicle information includes, for example, the vehicle class described above.

The extraction unit 232 extracts the type of dangerous event from the video collected by the collection unit 231 . The extraction unit 232 extracts the type of dangerous event by image recognition or the like.

For example, the dangerous event type may be information similar to the danger type of the danger information 221 . In that case, the types of dangerous events include sudden start, sudden steering, sudden braking, lane departure, and the like.

The calculation unit 233 calculates the degree of risk of behavior of the vehicle based on the detection information and the vehicle information. In this way, the information providing device 20 can accurately calculate the degree of danger by considering vehicle information as well as detection information.

The calculation unit 233 performs calculation regarding the type of dangerous event extracted by the extraction unit 232 as part of the detection information. That is, the calculation unit 233 calculates the degree of risk of vehicle behavior based on the detection information including the type of dangerous event extracted by the extraction unit 232 .

In this way, if the type of dangerous event can be extracted from the video, the accuracy of calculation can be further improved.

The calculation unit 233 calculates the degree of risk of behavior of the vehicle based on vehicle information including physical characteristics of the vehicle. For example, the calculation unit 233 calculates the degree of danger of behavior of the vehicle based on the vehicle class and load capacity, which are the physical characteristics of the vehicle.

For example, even if the G value is the same, the probability of an accident occurring may not always be the same depending on the vehicle class. The information providing device 20 can more accurately calculate the degree of danger by referring to physical characteristics such as vehicle class.

For example, the calculation unit 233 calculates the degree of danger by weighting the value calculated from the detection information based on the physical characteristics of the vehicle included in the vehicle information.

For example, the calculation unit 233 can calculate the degree of danger by multiplying the G value by a weight corresponding to the vehicle class.

An example of score calculation by the calculator 233 will be described with reference to FIGS. 4 and 5. FIG. 4 and 5 are diagrams showing examples of score calculation.

As shown in FIG. 4, it is assumed that a G value of 0.3 is detected by an in-vehicle device mounted on a vehicle classified as a "light vehicle." At this time, the vehicle information indicates that the vehicle class is a "light vehicle."

It is also assumed that the extraction unit 232 has extracted “sudden steering wheel” from the video as the type of dangerous event. Therefore, the detection information is that the G value is 0.3 and that a "sudden steering" has been performed.

From the danger information 221, the calculation unit 233 counts the number of accidents that occur when the detection information and the vehicle information are common. As shown in FIG. 3, when the G value is "0.3", the danger type is "sharp steering", and the vehicle class is "light vehicle", the number of accidents is three.

The calculation unit 233 calculates a score by multiplying the G value by the number of occurrences as a weight. In the example of FIG. 4, the calculation unit 233 calculates the score as 0.3 (G value)×3 (number of occurrences)=0.9.

Next, as shown in FIG. 5, it is assumed that a G value of 1.0 is detected by an in-vehicle device mounted on a vehicle classified as "large vehicle". At this time, the vehicle information indicates that the vehicle class is a "large vehicle".

It is also assumed that the extraction unit 232 has extracted “sudden steering wheel” from the video as the type of dangerous event. Therefore, the detection information is that the G value is 1.0 and that a "sudden steering" has been performed.

From the danger information 221, the calculation unit 233 counts the number of accidents that occur when the detection information and the vehicle information are common. As shown in FIG. 3, when the G value is "1.0", the danger type is "sharp steering", and the vehicle class is "large vehicle", the number of accidents is zero.

The calculation unit 233 calculates a score by multiplying the G value by the number of occurrences as a weight. In the example of FIG. 5, the calculation unit 233 calculates the score as 1.0 (G value)×0 (number of occurrences)=0.

The degree of danger is generally considered to be proportional to the detected G value. However, as in the examples of FIGS. 4 and 5, when vehicle information such as vehicle class is taken into consideration, it is possible that the magnitude relationship of the G value and the magnitude relationship of the degree of danger are reversed.

In addition, depending on past cases, the reversal of the magnitude relationship does not necessarily occur. Conversely, a larger weight may be applied to a case where the vehicle class is a “large vehicle”.

Note that the calculation unit 233 may calculate the score using a machine learning model that learns data such as the danger information 221 shown in FIG.

For example, the machine learning model takes as input (explanatory variables) the vehicle class, loading state, danger type, and G value of the danger information 221, and binary values (occurrence: 1, non-occurrence: 0) representing the occurrence or non-occurrence of an accident. is the output (objective variable).

Further, the calculation unit 233 calculates the degree of risk of behavior of the vehicle based on the detection information, the vehicle information, and the information indicating the driving environment of the vehicle.

For example, it is considered that the degree of danger changes depending on the weather, the driving area, the narrowness of the road, and the like. The calculation unit 233 can calculate a more realistic degree of danger by taking into account information about the environment in addition to the detection information and the vehicle information.

Further, the calculation unit 233 may calculate the degree of danger based on information about the driver, such as the driver's age and driving history.

FIG. 6 is a flow chart showing a processing procedure of the information providing device according to the embodiment. As shown in FIG. 6, first, the information providing device 20 collects detection information and vehicle information from the in-vehicle device (step S101).

Next, the information providing device 20 calculates a value from the detection information (step S102). The value calculated here may be the G value itself.

Then, the information providing device 20 weights the value with the vehicle information (step S103). For example, the information providing device 20 multiplies a weight based on the number of past accidents for each vehicle class.

Furthermore, the information providing device 20 notifies the calculation result (step S104).

As described above, the information providing device 20 has the collection unit 231 and the calculation unit 233 . The collection unit 231 collects detection information including sensor values detected by an in-vehicle device mounted in the vehicle, and vehicle information about the vehicle. The calculation unit 233 calculates the degree of risk of behavior of the vehicle based on the detection information and the vehicle information.

In this way, the information providing device 20 calculates the degree of danger in consideration of vehicle information as well as detection information. As a result, according to the present embodiment, it is possible to accurately calculate the degree of risk of behavior of the vehicle.

Each function of the information providing device 20 is realized by a computer or various circuits having, for example, a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), flash memory, input/output ports, and the like. be.

Further, the information providing apparatus 20 may acquire the above-described programs and various types of information via other computers or portable recording media connected via a wired or wireless network.

The CPU of the computer functions as a collection unit 231, an extraction unit 232, a calculation unit 233, and a notification unit 234 by reading and executing programs stored in the ROM, for example.

Further effects and modifications can be easily derived by those skilled in the art. Therefore, the broader aspects of the invention are not limited to the specific details and representative embodiments shown and described above. Accordingly, various changes may be made without departing from the spirit or scope of the general inventive concept defined by the appended claims and equivalents thereof.

N network V vehicle 1 information providing system 10 in-vehicle device 20 information providing device 21 interface unit 22 storage unit 23 control unit 30 terminal 221 danger information 231 collection unit 232 extraction unit 233 calculation unit 234 notification unit

Claims (7)

a collection unit that collects detection information including sensor values detected by an in-vehicle device mounted in a vehicle and vehicle information about the vehicle;
a calculation unit that calculates a risk degree of behavior of the vehicle based on the detection information and the vehicle information;
An information providing device characterized by comprising: The collection unit further collects images captured by the in-vehicle device,
further comprising an extraction unit for extracting a type of dangerous event from the video collected by the collection unit;
2. The provision of information according to claim 1, wherein the calculation unit calculates the degree of danger of behavior of the vehicle based on the detection information including the type of the dangerous event extracted by the extraction unit. Device. 3. The information providing apparatus according to claim 1, wherein the calculation unit calculates the degree of risk of behavior of the vehicle based on the vehicle information including physical characteristics of the vehicle. 4. The information providing apparatus according to claim 3, wherein the calculation unit calculates the degree of danger of the behavior of the vehicle based on the vehicle class and load capacity, which are physical characteristics of the vehicle. 2. The calculating unit calculates the degree of risk by weighting the value calculated from the detection information based on physical characteristics of the vehicle included in the vehicle information. 5. The information providing device according to any one of 4. 6. The method according to claim 1, wherein the calculation unit calculates the degree of danger of behavior of the vehicle based on the detection information, the vehicle information, and information indicating the driving environment of the vehicle. The information providing device according to any one of items 1 and 2. An information providing system having an in-vehicle device and an information providing device,
The in-vehicle device
A transmission unit that transmits detection information including sensor values and vehicle information related to the vehicle to the information providing device,
The information providing device is
a collection unit that collects the detection information and the vehicle information from the in-vehicle device;
a calculation unit that calculates a risk degree of behavior of the vehicle based on the detection information and the vehicle information;
An information providing system characterized by comprising:

Images